BLOG
TBC

The term “mind control” may conjure up images of magicians and hypnotherapists, but where prosthetics are concerned, it represents hope. 


Researchers have been developing mind-controlled prosthetics for more than a decade with the aim of dramatically improving functionality for the user.

An MIT Technology Review article from March 2020 outlines the powerful potential of machine learning for such an endeavour, and the challenges faced by scientists in the process:


"Until now scientists have faced a major barrier: they haven’t been able to access nerve signals that are strong or stable enough to send to the bionic limb. Although it’s possible to get this sort of signal using a brain-machine interface, the procedure to implant one is invasive and costly. And the nerve signals carried by the peripheral nerves that fan out from the brain and spinal cord are too small.


"A new implant gets around this problem by using machine learning to amplify these signals. A study, published in Science Translational Medicine, found that it worked for four amputees for almost a year. It gave them fine control of their prosthetic hands and let them pick up miniature play bricks, grasp items like soda cans, and play Rock, Paper, Scissors."


Whilst it’s only a proof-of-concept study at present, the “how” makes for fascinating reading, and serves to illustrate how the large-scale implementation of such technology could be truly life-changing in the future.


"The procedure for the implant requires one of the amputee’s peripheral nerves to be cut and stitched up to the muscle. The site heals, developing nerves and blood vessels over three months. Electrodes are then implanted into these sites, allowing a nerve signal to be recorded and passed on to a prosthetic hand in real time. The signals are turned into movements using machine-learning algorithms (the same types that are used for brain-machine interfaces).


"Amputees wearing the prosthetic hand were able to control each individual finger and swivel their thumbs, regardless of how recently they had lost their limb. Their nerve signals were recorded for a few minutes to calibrate the algorithms to their individual signals, but after that each implant worked straight away, without any need to recalibrate during the 300 days of testing."


A study published in April 2020 in the New England Journal of Medicine focused on patients who'd lived with a bone-anchored, self-contained robotic arm for between three and seven years, and had experienced sensations of touch for the first time as a result.


e-OPRA, the implant system used for the study, was created by Swedish company Integrum AB and relies upon “intuitive control”, whereby signals are fed to sensors wrapped around nerves, which in turn create a “feeling” of touch in the brain.


Using a process called osseointegration – in which bone cells are attached to an artificial surface without the formation of fibrous tissue – recipients of the device also enjoyed greater freedom of movement, with all four patients reporting a greater trust in their prosthetic, combined with positive effects on their self-esteem, self-image, and social relations:


"Use of the device did not require formal training and depended on the intuitive intent of the user to activate movement and sensory feedback from the prosthesis. Daily use resulted in increasing sensory acuity and effectiveness in work and other activities of daily life."


And we’re not just talking tea-making here. Stat News reported patients were able to race and repair cars, canoe, ice fish and ride a snowmobile thanks to the improved hand control afforded by the new prosthesis.


It’s all mightily impressive, and provides an exciting insight into the endless possibilities that AI offers in the medical field.


As with most pioneering solutions, however, there are significant challenges.

Despite no serious adverse effects being reported by the patients in the study, the potential risk of infection has caused delays in receiving U.S. approval for the system.


There is also the question of cost.


Dr. James Clune, a specialist surgeon at Yale Medicine, told Healthline that it’s “not a question of if this technology will be used here [in the U.S.], but when.” He continues:


"The difference in cost between a body-powered limb and an osseointegrated externally powered limb are exponentially different. Thus, there is an uphill battle to bring osseointegrated limbs to market here in the U.S."


One solution proposed by Clune is to surgically prepare the nerves in the limbs of patients who cannot currently attain an advanced prosthetic, ready for the use of emerging technologies in the future.


Dr. Adnan Prsic, also of Yale Medicine, adds:


"It is my hope to see myoelectric technology, both osseointegrated and non, become affordable and then widely available for all that need them, and not just for those that can afford to pay the heavy price tag."


With results as promising as these early studies, I’m sure many will feel it’s worth the wait to wave goodbye to conventional prostheses forever.


Elon Musk certainly knows the value of playing the long game.


In 2016, Musk founded Neuralink with the aim of “developing ultra-high bandwidth brain-machine interfaces to connect humans and computers.” Or, in other words, implanting tiny computer chips into people’s brains to improve their quality of life.


Imagine switching a light bulb on using only the power of your mind. Or being able to instantly speak a different language without ever learning it. Sounds like something from a sci-fi movie, doesn’t it? But one day – in the not-too-distant future -  this could become a reality.


In theory, by connecting an electrode to an individual neuron, it is possible to modify what signal it sends – and even send signals back! But it will take time. Human brains contain around 86 billion neurons, so - if past trends are to go by - it could be another 200 years before we’ve successfully mapped every single one.


Whenever it does happen, one thing is for sure – our lives will never be the same again…

  • LinkedIn
  • Twitter
  • YouTube